Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds a genuinely non-obvious behavioral fact beyond that: reading has no side effect on the underlying job and will not trigger or duplicate a model call, which matters for a hosted async job.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences, zero filler, with the core action front-loaded and the no-side-effect caveat immediately after. Nothing could be cut without losing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return shape need not be explained, and annotations cover the safety profile. The description covers what the tool does and its key non-side-effect guarantee; only an explicit pointer to how the run_id is obtained and a sibling contrast are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so run_id and the project_id fallback are already documented in the schema. The description adds no additional syntax, format, or selection guidance for either parameter, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb ('Read') and resource ('status of a hosted review job'), so the agent knows this is a status-query tool rather than one that produces a review. It does not explicitly contrast with close siblings like get_page_review or get_task, but the resource is specific enough to route correctly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence ('Reading does not start or repeat a model call') implies this is the safe polling path when a job is already underway, which is useful implied guidance. However, it never states when to prefer this over get_page_review or how to obtain a run_id in the first place, so usage is inferred rather than instructed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.